Abstract. Ambitious driver assistance for complex urban scenarios demands a complete awareness of the situation, including all moving and stationary objects that limit the free space. Recent progress in real-time dense stereo vision provides precise depth information for nearly every pixel of an image. This rises new questions: How can one efficiently analyze half a million disparity values of next generation imagers? And how can one find all relevant obstacles in this huge amount of data in real-time? In this paper we build a medium-level representation named "stixel-world". It takes into account that the free space in front of vehicles is limited by objects with almost vertical surfaces. These surfaces are approximated by adjacent rectangular sticks of a certain width and height. The stixel-world turns out to be a compact but flexible representation of the three-dimensional traffic situation that can be used as the common basis for the scene understanding tasks of driver assistance and autonomous systems.

Abstract-One of the fundamental requirements of an autonomous vehicle is the ability to determine its location on a map. Frequently, solutions to this localization problem rely on GPS information or use expensive three dimensional (3D) sensors. In this paper, we describe a method for long-term vehicle localization based on visual features alone. Our approach utilizes a combination of topological and metric mapping, which we call topometric localization, to encode the coarse topology of the route as well as detailed metric information required for accurate localization. A topometric map is created by driving the route once and recording a database of visual features. The vehicle then localizes by matching features to this database at runtime. Since individual feature matches are unreliable, we employ a discrete Bayes filter to estimate the most likely vehicle position using evidence from a sequence of images along the route. We illustrate the approach using an 8.8 km route through an urban and suburban environment. The method achieves an average localization error of 2.7 m over this route, with isolated worst case errors on the order of 10 m.

Abstract-Autonomous vehicles must be capable of localizing even in GPS denied situations. In this paper, we propose a realtime method to localize a vehicle along a route using visual imagery or range information. Our approach is an implementation of topometric localization, which combines the robustness of topological localization with the geometric accuracy of metric methods. We construct a map by navigating the route using a GPS-equipped vehicle and building a compact database of simple visual and 3D features. We then localize using a Bayesian filter to match sequences of visual or range measurements to the database. The algorithm is reliable across wide environmental changes, including lighting differences, seasonal variations, and occlusions, achieving an average localization accuracy of 1 m over an 8 km route. The method converges correctly even with wrong initial position estimates solving the kidnapped robot problem.

This paper presents a novel stereo-based visual odometry approach that provides state-of-the-art results in real time, both indoors and outdoors. Our proposed method follows the procedure of computing optical flow and stereo disparity to minimize the re-projection error of tracked feature points. However, instead of following the traditional approach of performing this task using only consecutive frames, we propose a novel and computationally inexpensive technique that uses the whole history of the tracked feature points to compute the motion of the camera. In our technique, which we call multi-frame feature integration, the features measured and tracked over all past frames are integrated into a single, improved estimate. An augmented feature set, composed of the improved estimates, is added to the optimization algorithm, improving the accuracy of the computed motion and reducing ego-motion drift. Experimental results show that the proposed approach reduces pose error by up to 65% with a negligible additional computational cost of 3.8%. Furthermore, our algorithm outperforms all other known methods on the KITTI Vision Benchmark data set.

No abstract